Learning CPG-based biped locomotion with a policy gradient method

Recently, CPG-based controllers have been widely explored to achieve robust biped locomotion. However, this approach has difficulties in tuning open parameters in the controller. In this paper, we present a learning framework for CPG-based biped locomotion with a policy gradient method. We demonstrate that appropriate sensory feedback in the CPG-based control architecture can be acquired using the proposed method within a thousand trials by numerical simulations. We analyze linear stability of a periodic orbit of the acquired biped walking considering a return map. Furthermore, we apply the learned controllers in numerical simulations to our physical 5-link robot in order to empirically evaluate the effectiveness of the proposed framework. Experimental results suggest the robustness of the acquired controllers against environmental changes and variations in the mass properties of the robot